© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208822
    Prev
    Next
    INDEX
    Explanations

    empty spaces or blank slate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_19_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    機能
    0.47
    க்குற
    0.47
     منظر
    0.46
     –
    0.45
    urricular
    0.43
    dling
    0.42
    ault
    0.41
    elizmente
    0.40
    alter
    0.40
     frivol
    0.40
    POSITIVE LOGITS
    пу
    0.45
     испыта
    0.42
     ENS
    0.42
    ха
    0.40
     neutralization
    0.39
    OCI
    0.39
     Raw
    0.38
    حت
    0.38
    __*/
    0.38
    ೋತಿ
    0.38
    Activations Density 0.028%

    No Known Activations